© Neuronpedia 2026
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Neuronpedia
Jacobian Lens
NEW
Natural Language
Autoencoders
NEW
Assistant Axis
NEW
Circuit Tracer
UPDATE
Releases
Jump To
Search
Steer
SAE Evals
Exports
interp-engine
NEW
Guides
API
Community
Blog
Privacy & Terms
Contact
Sign In
LLAMA3-8B-IT · 25-RES-JH · 12979 ｜ Neuronpedia
Home
Julius Han · Gated SAE for Llama3-8B-Instruct
Llama3-8B-IT
Residual Stream
25-RES-JH
12979
Prev
Next
MODEL
25-res-jh
Source/SAE
INDEX
Go
Explanations
quotations that convey significant statements or perspectives
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Interpretable Score
Intrusion Detection
Top Features by Cosine Similarity
Configuration
Juliushanhanhan/llama-3-8b-it-res/blocks.25.hook_resid_post
How To Load
Features
65,536
Data Type
float32
Hook Name
blocks.25.hook_resid_post
Hook Layer
25
Architecture
gated
Context Size
1,024
Dataset
Juliushanhanhan/openwebtext-1b-llama3-tokenized-cxt-1024
Activation Function
relu
Show All
Embeds
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/llama3-8b-it/25-res-jh/12979?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/llama3-8b-it/25-res-jh/12979?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
"
-0.27
"'
-0.23
("
-0.20
"_
-0.19
"\(
-0.18
ï¼ļ"
-0.18
("
-0.18
-"
-0.17
"#
-0.17
/"
-0.17
POSITIVE LOGITS
s
0.22
a
0.21
e
0.18
we
0.15
‘
0.15
an
0.15
t
0.15
’
0.15
er
0.15
(
0.14
Act
ivations
Density 0.250%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
